Arm has extended its Cortex-M portfolio to bring AI to the smallest endpoint devices. The company has announced the launch of the Arm Cortex-M52, designed for AIoT applications that require boosted digital signal processing (DSP) and ML performance without the cost overhead of dedicated DSP and ML accelerators.

According to Arm, Cortex-M52 will unlock the potential for delivering ML on embedded computing solutions at lower price points than is possible today.

The Cortex-M52 includes Arm Helium technology, providing a performance uplift in DSP and ML applications for small, low power embedded devices. This will make it possible to deploy more compute intensive ML inference algorithms in endpoints without a dedicated NPU.

Helium technology has already been implemented successfully in products at the far edge of the network, but the Cortex-M52 now enables this capability in lower cost more power constrained devices.

The Cortex-M52 is designed to provide a simplified migration path from the Cortex-M33 and Cortex-M4, addressing a range of AIoT applications to enable improved UI, voice and vision experiences, such as automotive and industrial control, predictive maintenance, and wearable sensor fusion.

Cortex-M52 implements security extensions for Armv8.1-M including PACBTI and Arm TrustZone technology, which offers enhanced software threat mitigation. It will also accelerate the route to PSA Certified Level 2 silicon, enabling the next generation of PSA Certified devices.

Cortex-M52 is software compatible with Cortex-M55 and Cortex-M85. To help streamline and accelerate the IoT and embedded development process, Cortex-M52 will also be available on Arm Virtual Hardware, Arm’s cloud-based virtual silicon software development platform.